Winding is one of themost important components in power transformers.Ensuring the health state of the winding is of great importance to the stable operation of the power system.To efficiently and accurately diagnose t...Winding is one of themost important components in power transformers.Ensuring the health state of the winding is of great importance to the stable operation of the power system.To efficiently and accurately diagnose the disc space variation(DSV)fault degree of transformer winding,this paper presents a diagnostic method of winding fault based on the K-Nearest Neighbor(KNN)algorithmand the frequency response analysis(FRA)method.First,a laboratory winding model is used,and DSV faults with four different degrees are achieved by changing disc space of the discs in the winding.Then,a series of FRA tests are conducted to obtain the FRA results and set up the FRA dataset.Second,ten different numerical indices are utilized to obtain features of FRA curves of faulted winding.Third,the 10-fold cross-validation method is employed to determine the optimal k-value of KNN.In addition,to improve the accuracy of the KNN model,a comparative analysis is made between the accuracy of the KNN algorithm and k-value under four distance functions.After getting the most appropriate distance metric and kvalue,the fault classificationmodel based on theKNN and FRA is constructed and it is used to classify the degrees of DSV faults.The identification accuracy rate of the proposed model is up to 98.30%.Finally,the performance of the model is presented by comparing with the support vector machine(SVM),SVM optimized by the particle swarmoptimization(PSO-SVM)method,and randomforest(RF).The results show that the diagnosis accuracy of the proposed model is the highest and the model can be used to accurately diagnose the DSV fault degrees of the winding.展开更多
高光谱成像技术的飞速发展给非侵入式医学成像带来新的契机,但高光谱医学图像具有高维度、高冗余以及“图谱合一”的特点,亟需针对上述特点设计智能诊断算法。近年来,Transformer已经在高光谱医学图像处理领域得到广泛应用。然而,不同...高光谱成像技术的飞速发展给非侵入式医学成像带来新的契机,但高光谱医学图像具有高维度、高冗余以及“图谱合一”的特点,亟需针对上述特点设计智能诊断算法。近年来,Transformer已经在高光谱医学图像处理领域得到广泛应用。然而,不同仪器设备、不同采集操作所获得的高光谱医学图像差异较大,这给现有Transformer诊断模型的实际应用带来了巨大挑战。针对上述问题,本文提出了一种空-谱自注意力Transformer(S3AT),自适应挖掘像素与像素间、波段与波段间的内蕴联系,并在分类阶段融合多个视野下的预测结果。首先,在Transformer编码器中,设计一种空-谱自注意力机制,获取不同视野下高光谱图像上的关键空间信息和重要波段,并将不同视野下所获得的空-谱自注意力进行融合。其次,在模型分类阶段,将不同视野下的预测结果根据可学习权重进行加权融合,对图像进行综合预测。在In-vivo Human Brain和BloodCell HSI两个数据集上,本文算法总体分类精度分别达到82.25%和91.74%。实验结果表明,所提出的算法有效改善高光谱医学图像分类性能。展开更多
It is difficult to accurately calculate the short-circuit impedance, due to the complexity of axial dual-low-voltage split-winding transformer winding structure. In this paper, firstly, the leakage magnetic field and ...It is difficult to accurately calculate the short-circuit impedance, due to the complexity of axial dual-low-voltage split-winding transformer winding structure. In this paper, firstly, the leakage magnetic field and short-circuit impedance model of axial dual-low-voltage split-winding transformer is established, and then the 2D and 3D leakage magnetic field are analyzed. Secondly, the short-circuit impedance and split parallel branch current distribution in different working conditions are calculated, which is based on field-circuit coupled method. At last, effectiveness and feasibility of the proposed model is verified by comparison between experiment, analysis and simulation. The results showed that the 3D analysis method is a better approach to calculate the short-circuit impedance, since its analytical value is more closer to the experimental value compared with the 2D analysis results, the finite element method calculation error is less than 2%, while the leakage flux method maximum error is 7.2%.展开更多
负荷预测是综合能源系统(integrated energy system,IES)能量管理和优化调度的基础,其预测精度直接关系到系统的整体运行性能。提出了一种基于Transformer网络和多任务学习的园区综合能源系统电-热短期负荷预测模型。首先对Transformer...负荷预测是综合能源系统(integrated energy system,IES)能量管理和优化调度的基础,其预测精度直接关系到系统的整体运行性能。提出了一种基于Transformer网络和多任务学习的园区综合能源系统电-热短期负荷预测模型。首先对Transformer网络和多任务学习结构的基本原理进行了介绍;然后通过基于随机森林的特征选择步骤提取反映负荷特性和变化规律的典型指标,构建多任务学习输入特征,基于Transformer网络构建多任务学习权值共享层,并通过全连接层输出多能负荷的预测值;最后通过实际园区微能源系统的数据验证所提方法和算法的有效性,结果表明本文所提模型可以充分学习电-热耦合特征,提高负荷预测的精度。展开更多
Wind turbine planetary gearboxes usually work under time-varying conditions,leading to nonstationary vibration signals.These signals often consist of multiple time-varying components with close instantaneous frequenci...Wind turbine planetary gearboxes usually work under time-varying conditions,leading to nonstationary vibration signals.These signals often consist of multiple time-varying components with close instantaneous frequencies.Therefore,high-quality time-frequency analysis(TFA)is needed to extract the time-frequency feature from such nonstationary signals for fault diagnosis.However,it is difficult to obtain high-quality timefrequency representations(TFRs)through conventional TFA methods due to low resolution and time-frequency blurs.To address this issue,we propose a new TFA method termed the proportion-extracting synchrosqueezing chirplet transform(PESCT).Firstly,the proportion-extracting chirplet transform is employed to generate highresolution underlying TFRs.Then,the energy concentration of the underlying TFRs is enhanced via the synchrosqueezing transform.Finally,wind turbine planetary gearbox fault can be diagnosed by analysis of the dominant time-varying components revealed by the concentrated TFRs with high resolution.The proposed PESCT is suitable for achieving high-quality TFRs for complicated nonstationary signals.Numerical and experimental analyses validate the effectiveness of the PESCT in characterizing the nonstationary signals from wind turbine planetary gearboxes.展开更多
文章研究了基于Transformer模型的中文文本生成方法,重点探讨了Transformer模型的编码器-解码器结构及其工作原理。在详细分析了编码器和解码器的工作机制后,文章利用Hugging Face Transformers开源模型进行了中文文本生成实验。结果表...文章研究了基于Transformer模型的中文文本生成方法,重点探讨了Transformer模型的编码器-解码器结构及其工作原理。在详细分析了编码器和解码器的工作机制后,文章利用Hugging Face Transformers开源模型进行了中文文本生成实验。结果表明,该方法在自制数据集上取得了良好的效果,其准确率、精确率和召回率分别达到92.5%、91.8%和90.6%。该研究不仅拓展了中文自然语言处理的理论基础,还为实际应用提供了高效的技术支持。展开更多
基金supported in part by Shaanxi Natural Science Foundation Project (2023-JC-QN-0438)in part by Fundamental Research Funds for the Central Universities (2452021050).
文摘Winding is one of themost important components in power transformers.Ensuring the health state of the winding is of great importance to the stable operation of the power system.To efficiently and accurately diagnose the disc space variation(DSV)fault degree of transformer winding,this paper presents a diagnostic method of winding fault based on the K-Nearest Neighbor(KNN)algorithmand the frequency response analysis(FRA)method.First,a laboratory winding model is used,and DSV faults with four different degrees are achieved by changing disc space of the discs in the winding.Then,a series of FRA tests are conducted to obtain the FRA results and set up the FRA dataset.Second,ten different numerical indices are utilized to obtain features of FRA curves of faulted winding.Third,the 10-fold cross-validation method is employed to determine the optimal k-value of KNN.In addition,to improve the accuracy of the KNN model,a comparative analysis is made between the accuracy of the KNN algorithm and k-value under four distance functions.After getting the most appropriate distance metric and kvalue,the fault classificationmodel based on theKNN and FRA is constructed and it is used to classify the degrees of DSV faults.The identification accuracy rate of the proposed model is up to 98.30%.Finally,the performance of the model is presented by comparing with the support vector machine(SVM),SVM optimized by the particle swarmoptimization(PSO-SVM)method,and randomforest(RF).The results show that the diagnosis accuracy of the proposed model is the highest and the model can be used to accurately diagnose the DSV fault degrees of the winding.
文摘高光谱成像技术的飞速发展给非侵入式医学成像带来新的契机,但高光谱医学图像具有高维度、高冗余以及“图谱合一”的特点,亟需针对上述特点设计智能诊断算法。近年来,Transformer已经在高光谱医学图像处理领域得到广泛应用。然而,不同仪器设备、不同采集操作所获得的高光谱医学图像差异较大,这给现有Transformer诊断模型的实际应用带来了巨大挑战。针对上述问题,本文提出了一种空-谱自注意力Transformer(S3AT),自适应挖掘像素与像素间、波段与波段间的内蕴联系,并在分类阶段融合多个视野下的预测结果。首先,在Transformer编码器中,设计一种空-谱自注意力机制,获取不同视野下高光谱图像上的关键空间信息和重要波段,并将不同视野下所获得的空-谱自注意力进行融合。其次,在模型分类阶段,将不同视野下的预测结果根据可学习权重进行加权融合,对图像进行综合预测。在In-vivo Human Brain和BloodCell HSI两个数据集上,本文算法总体分类精度分别达到82.25%和91.74%。实验结果表明,所提出的算法有效改善高光谱医学图像分类性能。
文摘It is difficult to accurately calculate the short-circuit impedance, due to the complexity of axial dual-low-voltage split-winding transformer winding structure. In this paper, firstly, the leakage magnetic field and short-circuit impedance model of axial dual-low-voltage split-winding transformer is established, and then the 2D and 3D leakage magnetic field are analyzed. Secondly, the short-circuit impedance and split parallel branch current distribution in different working conditions are calculated, which is based on field-circuit coupled method. At last, effectiveness and feasibility of the proposed model is verified by comparison between experiment, analysis and simulation. The results showed that the 3D analysis method is a better approach to calculate the short-circuit impedance, since its analytical value is more closer to the experimental value compared with the 2D analysis results, the finite element method calculation error is less than 2%, while the leakage flux method maximum error is 7.2%.
文摘负荷预测是综合能源系统(integrated energy system,IES)能量管理和优化调度的基础,其预测精度直接关系到系统的整体运行性能。提出了一种基于Transformer网络和多任务学习的园区综合能源系统电-热短期负荷预测模型。首先对Transformer网络和多任务学习结构的基本原理进行了介绍;然后通过基于随机森林的特征选择步骤提取反映负荷特性和变化规律的典型指标,构建多任务学习输入特征,基于Transformer网络构建多任务学习权值共享层,并通过全连接层输出多能负荷的预测值;最后通过实际园区微能源系统的数据验证所提方法和算法的有效性,结果表明本文所提模型可以充分学习电-热耦合特征,提高负荷预测的精度。
基金the National Natural Science Foundation of China(52275080)。
文摘Wind turbine planetary gearboxes usually work under time-varying conditions,leading to nonstationary vibration signals.These signals often consist of multiple time-varying components with close instantaneous frequencies.Therefore,high-quality time-frequency analysis(TFA)is needed to extract the time-frequency feature from such nonstationary signals for fault diagnosis.However,it is difficult to obtain high-quality timefrequency representations(TFRs)through conventional TFA methods due to low resolution and time-frequency blurs.To address this issue,we propose a new TFA method termed the proportion-extracting synchrosqueezing chirplet transform(PESCT).Firstly,the proportion-extracting chirplet transform is employed to generate highresolution underlying TFRs.Then,the energy concentration of the underlying TFRs is enhanced via the synchrosqueezing transform.Finally,wind turbine planetary gearbox fault can be diagnosed by analysis of the dominant time-varying components revealed by the concentrated TFRs with high resolution.The proposed PESCT is suitable for achieving high-quality TFRs for complicated nonstationary signals.Numerical and experimental analyses validate the effectiveness of the PESCT in characterizing the nonstationary signals from wind turbine planetary gearboxes.
文摘文章研究了基于Transformer模型的中文文本生成方法,重点探讨了Transformer模型的编码器-解码器结构及其工作原理。在详细分析了编码器和解码器的工作机制后,文章利用Hugging Face Transformers开源模型进行了中文文本生成实验。结果表明,该方法在自制数据集上取得了良好的效果,其准确率、精确率和召回率分别达到92.5%、91.8%和90.6%。该研究不仅拓展了中文自然语言处理的理论基础,还为实际应用提供了高效的技术支持。
